arXiv subjects

Xiaoxue Li

Publications and source records attributed to Xiaoxue Li.

9 recordsLinked to original sources

arXiv2026

Beyond Classification: Structured Supervision Aligns Visual Evidence with Medical Semantics

Vision Transformers (ViTs) have shown immense potential in medical image analysis. However, standard pre-training via global image classification suffers from spatial collapse, where models rely heavily on background shortcuts rather than localising critical foreground lesions. To overcome this limitation and align visual evidence with precise medical semantics, we systematically investigate alternative pre-training paradigms.Specifically, we evaluate three independent forms of structured supervision: topological priors via graph self-supervision, dense pixel-level constraints via segmentation, and cross-modal semantic grounding via image-text pairs. Notably, our empirical analysis reveals that while all three forms of structured supervision successfully alleviate the global pooling bottleneck and steer visual attention towards foreground regions, image-text alignment achieves the most superior performance. By embedding high-dimensional diagnostic logic, the cross-modal approach not only anchors attention on precise visual evidence but also enables profound abstract reasoning. Extensive experiments demonstrate that this semantically enriched pre-training fundamentally enhances the model's feature representation. Consequently, when fine-tuned for downstream clinical classification tasks, our models achieve superior accuracy and yield highly interpretable attention maps focused on true pathological features, vastly outperforming vanilla classification baselines.

cs.CV↗

arXiv2026

Implementing the principal stratum strategy for intercurrent events with survival outcomes: a tutorial

The International Council for Harmonization (ICH) E9 (R1) addendum provides the estimand framework to formulate treatment effects in a clinical trial. One of the attributes of an estimand the framework describes is intercurrent events. Among the five strategies to intercurrent events the guidance lists, the principal stratum strategy is the most conceptually and technically challenging because it defines treatment effects on unobserved strata. Its application to survival outcomes is particularly inaccessible to practitioners. This tutorial reviews the methodology and implementation of the estimand framework with the principal stratum strategy to address intercurrent events with survival outcomes. We illustrate using a clinical trial in oncology and focus on a simple case with binary treatment and a single binary intercurrent event of discontinuation of the assigned treatment. We define the causal effects and review two main methods for estimating the effects: the mixture model method and the weighting method. For each method, we elaborate the associated assumptions, models, sensitivity analysis, software and provide example R code. We conduct simulation studies that mimic the real study to study the operation characteristics of these methods.

stat.ME↗

arXiv2026

Rethinking LLM Watermark Detection in Black-Box Settings: A Non-Intrusive Third-Party Framework

While watermarking serves as a critical mechanism for LLM provenance, existing secret-key schemes tightly couple detection with injection, requiring access to keys or provider-side scheme-specific detectors for verification. This dependency creates a fundamental barrier for real-world governance, as independent auditing becomes impossible without compromising model security or relying on the opaque claims of service providers. To resolve this dilemma, we introduce TTP-Detect, a pioneering black-box framework designed for non-intrusive, third-party watermark verification. By decoupling detection from injection, TTP-Detect reframes verification as a relative hypothesis testing problem. It employs a proxy model to amplify watermark-relevant signals and a suite of complementary relative measurements to assess the alignment of the query text with watermarked distributions. Extensive experiments across representative watermarking schemes, datasets and models demonstrate that TTP-Detect achieves superior detection performance and robustness against diverse attacks.

cs.CR↗

arXiv2025

Reinforcement Learning on Pre-Training Data

The growing disparity between the exponential scaling of computational resources and the finite growth of high-quality text data now constrains conventional scaling approaches for large language models (LLMs). To address this challenge, we introduce Reinforcement Learning on Pre-Training data (RLPT), a new training-time scaling paradigm for optimizing LLMs. In contrast to prior approaches that scale training primarily through supervised learning, RLPT enables the policy to autonomously explore meaningful trajectories to learn from pre-training data and improve its capability through reinforcement learning (RL). While existing RL strategies such as reinforcement learning from human feedback (RLHF) and reinforcement learning with verifiable rewards (RLVR) rely on human annotation for reward construction, RLPT eliminates this dependency by deriving reward signals directly from pre-training data. Specifically, it adopts a next-segment reasoning objective, rewarding the policy for accurately predicting subsequent text segments conditioned on the preceding context. This formulation allows RL to be scaled on pre-training data, encouraging the exploration of richer trajectories across broader contexts and thereby fostering more generalizable reasoning skills. Extensive experiments on both general-domain and mathematical reasoning benchmarks across multiple models validate the effectiveness of RLPT. For example, when applied to Qwen3-4B-Base, RLPT yields absolute improvements of $3.0$, $5.1$, $8.1$, $6.0$, $6.6$, and $5.3$ on MMLU, MMLU-Pro, GPQA-Diamond, KOR-Bench, AIME24, and AIME25, respectively. The results further demonstrate favorable scaling behavior, suggesting strong potential for continued gains with more compute. In addition, RLPT provides a solid foundation, extending the reasoning boundaries of LLMs and enhancing RLVR performance.

cs.CL↗

arXiv2024

Using Deep Learning to Find the Next Unicorn: A Practical Synthesis

Startups often represent newly established business models associated with disruptive innovation and high scalability. They are commonly regarded as powerful engines for economic and social development. Meanwhile, startups are heavily constrained by many factors such as limited financial funding and human resources. Therefore, the chance for a startup to eventually succeed is as rare as "spotting a unicorn in the wild". Venture Capital (VC) strives to identify and invest in unicorn startups during their early stages, hoping to gain a high return. To avoid entirely relying on human domain expertise and intuition, investors usually employ data-driven approaches to forecast the success probability of startups. Over the past two decades, the industry has gone through a paradigm shift moving from conventional statistical approaches towards becoming machine-learning (ML) based. Notably, the rapid growth of data volume and variety is quickly ushering in deep learning (DL), a subset of ML, as a potentially superior approach in terms of capacity and expressivity. In this work, we carry out a literature review and synthesis on DL-based approaches, covering the entire DL life cycle. The objective is a) to obtain a thorough and in-depth understanding of the methodologies for startup evaluation using DL, and b) to distil valuable and actionable learning for practitioners. To the best of our knowledge, our work is the first of this kind.

q-fin.CP↗

arXiv2024

Faster Projected GAN: Towards Faster Few-Shot Image Generation

In order to solve the problems of long training time, large consumption of computing resources and huge parameter amount of GAN network in image generation, this paper proposes an improved GAN network model, which is named Faster Projected GAN, based on Projected GAN. The proposed network is mainly focuses on the improvement of generator of Projected GAN. By introducing depth separable convolution (DSC), the number of parameters of the Projected GAN is reduced, the training speed is accelerated, and memory is saved. Experimental results show that on ffhq-1k, art-painting, Landscape and other few-shot image datasets, a 20% speed increase and a 15% memory saving are achieved. At the same time, FID loss is less or no loss, and the amount of model parameters is better controlled. At the same time, significant training speed improvement has been achieved in the small sample image generation task of special scenes such as earthquake scenes with few public datasets.

cs.CV↗

arXiv2022

An explicit Hopf bifurcation criterion of fractional-order systems with order 1 < α < 2

A Hopf bifurcation criterion of fractional-order systems with order 1 < α < 2 is established in this paper, in which all conditions are explicitly expressed by parameters without solving the roots of the relevant characteristic polynomial of Hopf bifurcation conditions. It avoids the problem that existing methods may fail due to the computational complexity in the multi-parameter situation. The bifurcation hyper-surface of multi-parameter can be obtained directly.

math.DS↗

arXiv2021

Is There More Pattern in Knowledge Graph? Exploring Proximity Pattern for Knowledge Graph Embedding

Modeling of relation pattern is the core focus of previous Knowledge Graph Embedding works, which represents how one entity is related to another semantically by some explicit relation. However, there is a more natural and intuitive relevancy among entities being always ignored, which is that how one entity is close to another semantically, without the consideration of any explicit relation. We name such semantic phenomenon in knowledge graph as proximity pattern. In this work, we explore the problem of how to define and represent proximity pattern, and how it can be utilized to help knowledge graph embedding. Firstly, we define the proximity of any two entities according to their statistically shared queries, then we construct a derived graph structure and represent the proximity pattern from global view. Moreover, with the original knowledge graph, we design a Chained couPle-GNN (CP-GNN) architecture to deeply merge the two patterns (graphs) together, which can encode a more comprehensive knowledge embedding. Being evaluated on FB15k-237 and WN18RR datasets, CP-GNN achieves state-of-the-art results for Knowledge Graph Completion task, and can especially boost the modeling capacity for complex queries that contain multiple answer entities, proving the effectiveness of introduced proximity pattern.

cs.CL↗

arXiv2019

RLINK: Deep Reinforcement Learning for User Identity Linkage

User identity linkage is a task of recognizing the identities of the same user across different social networks (SN). Previous works tackle this problem via estimating the pairwise similarity between identities from different SN, predicting the label of identity pairs or selecting the most relevant identity pair based on the similarity scores. However, most of these methods ignore the results of previously matched identities, which could contribute to the linkage in following matching steps. To address this problem, we convert user identity linkage into a sequence decision problem and propose a reinforcement learning model to optimize the linkage strategy from the global perspective. Our method makes full use of both the social network structure and the history matched identities, and explores the long-term influence of current matching on subsequent decisions. We conduct experiments on different types of datasets, the results show that our method achieves better performance than other state-of-the-art methods.

cs.LG↗